Analisis Sentimen Layanan Aplikasi Pendidikan Menggunakan Multinomial Naive Bayes

The rapid development of educational technology has increased the use of e-learning applications such as Ruangguru, generating a large amount of user reviews on Google Play Store that can be utilized to evaluate service quality. This study aims to analyze the sentiment of Ruangguru user reviews using the Multinomial Naive Bayes algorithm. The research data consisted of 5,000 user reviews collected through web scraping techniques from Google Play Store. The data were processed through several preprocessing stages, including cleansing, case folding, tokenizing, stopword removal, normalization, and stemming. Furthermore, the reviews were transformed into numerical representations using the Term Frequency–Inverse Document Frequency (TF-IDF) method before the classification process was carried out. The results showed that the proposed model achieved an accuracy of 88.55% in classifying positive, negative, and neutral sentiments. Most users expressed positive opinions regarding the learning content and application usability, although several technical issues were still identified in negative reviews. This research contributes to the implementation of machine learning techniques for automatic and objective evaluation of digital education service quality based on user opinions.